| { |
| "best_metric": 0.457686920201459, |
| "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-1069", |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 1069, |
| "is_hyper_param_search": true, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.47, |
| "grad_norm": 10.753751754760742, |
| "learning_rate": 1.7977369076499405e-05, |
| "loss": 0.5382, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.94, |
| "grad_norm": 9.229598999023438, |
| "learning_rate": 1.612211942980184e-05, |
| "loss": 0.4947, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.4966508448123932, |
| "eval_matthews_correlation": 0.457686920201459, |
| "eval_runtime": 0.7777, |
| "eval_samples_per_second": 1341.196, |
| "eval_steps_per_second": 84.87, |
| "step": 1069 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 5345, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 500, |
| "total_flos": 37591763974848.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": { |
| "learning_rate": 1.983261872319697e-05, |
| "num_train_epochs": 5, |
| "per_device_train_batch_size": 8, |
| "seed": 17 |
| } |
| } |
|
|
